Presentation 2023-03-03
Implementation and Evaluation of Real-Time Network Traffic Anomaly Detection in Edge Device
Kota Tsuchie, Nobuyuki Nakamura, Taketsugu Yao,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) For intrusion detection to closed networks, NDR (Network Detection and Response) is an expected technology that analyzes network traffic. General NDR systems consist of traffic sensors at the network edge and an analyzing cloud server; however, in closed networks, they should be completed in edge devices to reduce detection delays. Therefore, we implement a real-time anomaly detection method on an edge device with limited computing resources. The method analyzes network traffic in units of flow and is activated on a VPU (Vision Processing Unit) hardware accelerator specialized in inferring deep learning models. We reveal the method's throughput and detectable anomaly traffic patterns by using actual network traffic. The result shows that if we mutually use two different operational models, device-oriented and network-oriented models, the proposed method detects various anomaly traffic patterns within 60 seconds up to 47 flows per second.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Closed Network / NDR / Network Edge / VPU / IoT
Paper # IN2022-107
Date of Issue 2023-02-23 (IN)

Conference Information
Committee IN / NS
Conference Date 2023/3/2(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Okinawa Convention Centre + Online
Topics (in Japanese) (See Japanese page)
Topics (in English) General
Chair Kunio Hato(Internet Multifeed) / Tetsuya Oishi(NTT)
Vice Chair Tsutomu Murase(Nagoya Univ.) / Takumi Miyoshi(Shibaura Insti of Tech.)
Secretary Tsutomu Murase(KDDI Research) / Takumi Miyoshi(Nagaoka Univ. of Tech.)
Assistant / Kotaro Mihara(NTT)

Paper Information
Registration To Technical Committee on Information Networks / Technical Committee on Network Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Implementation and Evaluation of Real-Time Network Traffic Anomaly Detection in Edge Device
Sub Title (in English)
Keyword(1) Closed Network
Keyword(2) NDR
Keyword(3) Network Edge
Keyword(4) VPU
Keyword(5) IoT
1st Author's Name Kota Tsuchie
1st Author's Affiliation Oki Electric Industry Co., Ltd.(OKI)
2nd Author's Name Nobuyuki Nakamura
2nd Author's Affiliation Oki Electric Industry Co., Ltd.(OKI)
3rd Author's Name Taketsugu Yao
3rd Author's Affiliation Oki Electric Industry Co., Ltd.(OKI)
Date 2023-03-03
Paper # IN2022-107
Volume (vol) vol.122
Number (no) IN-407
Page pp.pp.247-252(IN),
#Pages 6
Date of Issue 2023-02-23 (IN)